© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 606
    Prev
    Next
    INDEX
    Explanations

    light and beam

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     madre
    -0.10
    upro
    -0.08
    hand
    -0.08
     magnets
    -0.08
     Playground
    -0.08
     Needle
    -0.08
    aurus
    -0.08
    озд
    -0.08
     Wise
    -0.08
    cad
    -0.07
    POSITIVE LOGITS
    enment
    0.16
     shining
    0.15
     brighter
    0.14
    ighted
    0.13
    -eyed
    0.13
     illumin
    0.13
    ight
    0.12
    eyes
    0.12
    beam
    0.12
    bul
    0.12
    Activations Density 1.564%

    No Known Activations